Multi-copy-based task scheduling method and system for edge computing environment

A task scheduling and edge computing technology, applied in computing, program control design, multiprogramming devices, etc.

Pending Publication Date: 2020-07-07
NANJING UNIV
View PDF4 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, theoretical models based simply on the distribution of task execution times are not applicable to edge environments

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Multi-copy-based task scheduling method and system for edge computing environment
  • Multi-copy-based task scheduling method and system for edge computing environment
  • Multi-copy-based task scheduling method and system for edge computing environment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] The technical solution of the present invention will be further described below in conjunction with the accompanying drawings.

[0047] In application systems such as big data processing and machine learning, a job runs in stages, each stage contains a certain number of tasks, and the tasks can be distributed to each cluster for parallel execution. The delay of a small number of tasks will affect the completion of the current stage, thereby prolonging the The execution time of the entire job. Multi-copy parallel execution can alleviate the impact of slow tasks, but the existing task replication strategy for a single cluster is not suitable for unstable, highly dynamic and highly heterogeneous edge computing environments. The present invention proposes an edge computing environment-oriented task scheduling method based on multi-task copies to reduce the response delay of distributed jobs. First, the task replication and scheduling problem in the edge computing environme...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a multi-copy-based task scheduling method and a multi-copy-based task scheduling system for an edge computing environment. The multi-copy-based task scheduling method comprisesthe steps of: measuring and collecting execution states of tasks in each edge cluster regularly, and establishing a task time delay factor distribution probability model of the present cluster, wherein the task time delay factor distribution probability model describes resource performance of the cluster; based on a shortest remaining processing time principle and a fair sharing principle, estimating the number of copies required by executable tasks of each job; based on the current progress of each job and the resource performance of the cluster, allocating idle nodes of each cluster to eachtask by adopting an iterative allocation mode according to the estimated number of copies; and scheduling the tasks allocated to the nodes to the corresponding clusters for execution. By utilizing the method and the system, idle resources in the edge computing environment can be effectively utilized in a real system, and the operation time delay of the operation is reduced by reasonably setting atask copy.

Description

technical field [0001] The present invention relates to task scheduling and resource allocation in a job processing system in an edge computing environment, and in particular to a task scheduling method and a scheduling system for reducing big data processing application delay based on multiple copies in an edge computing environment. Background technique [0002] Nowadays, users interact with cloud data more frequently, and cloud service providers accelerate the construction of "edge" clusters while deploying backbone data centers. Google has 15 data centers around the world, and it has also been detected that more than 1,400 end servers from 139 countries serve end users; Alibaba Cloud has established 18 data centers, and its content distribution network products (CDN) cover more than 1200 accelerated servers, spanning multiple ISP networks on 6 continents. For IT service providers that rely on the cloud, various types of user data are increasingly scattered in multiple g...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06F9/48G06F9/50
CPCG06F9/4881G06F9/505G06F9/5072Y02D10/00
Inventor 钱柱中王甜甜陆桑璐
Owner NANJING UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap